Re:I used DALL·E 2 to generate a logo
by cloogshicer on Tuesday August 02, 2022 @03:48PM
(#32323392)
Doesn't the sample size for this have to be very large for it to make a difference? Genuine question.
[ Parent
| on HN ]
With semi-supervised learning a small amount of labeled data, can produce considerable improvement in accuracy:
https://en.wikipedia.org/wiki/Semi-supervised_learning
https://towardsdatascience.com/semi-supervised-learning-how-...
Re:I used DALL·E 2 to generate a logo
by cloogshicer on Thursday August 04, 2022 @01:29AM
(#32339659)
Thank you!
Sure, but there are millions of people on the DALLE waitlist, who would happily rate the output for better performance / more credits. The famous ImageNet data set only has 1.2M images.